BACKGROUND AND PURPOSE:Qualitative radiologic MR imaging review affords limited differentiation among types of pediatric posterior fossa brain tumors and cannot detect histologic or molecular subtypes, which could help to stratify treatment. This study aimed to improve current posterior fossa discrimination of histologic tumor type by using support vector machine classifiers on quantitative MR imaging features.

To determine if apparent diffusion coefficients (ADC) can discriminate between posterior fossa brain tumours on a multicentre basis. A total of 124 paediatric patients with posterior fossa tumours (including 55 Medulloblastomas, 36 Pilocytic Astrocytomas and 26 Ependymomas) were scanned using diffusion weighted imaging across 12 different hospitals using a total of 18 different scanners. Apparent diffusion coefficient maps were produced and histogram data was extracted from tumour regions of interest. Total histograms and histogram metrics (mean, variance, skew, kurtosis and 10th, 20th and 50th quantiles) were used as data input for classifiers with accuracy determined by tenfold cross validation. Mean ADC values from the tumour regions of interest differed between tumour types, (ANOVA P < 0.001). A cut off value for mean ADC between Ependymomas and Medulloblastomas was found to be of 0.984 × 10−3 mm2 s−1 with sensitivity 80.8% and specificity 80.0%. Overall classification for the ADC histogram metrics were 85% using Naïve Bayes and 84% for Random Forest classifiers. The most commonly occurring posterior fossa paediatric brain tumours can be classified using Apparent Diffusion Coefficient histogram values to a high accuracy on a multicentre basis.

Purpose3T magnetic resonance scanners have boosted clinical application of 1H‐MR spectroscopy (MRS) by offering an improved signal‐to‐noise ratio and increased spectral resolution, thereby identifying more metabolites and extending the range of metabolic information. Spectroscopic data from clinical 1.5T MR scanners has been shown to discriminate between pediatric brain tumors by applying machine learning techniques to further aid diagnosis. The purpose of this multi‐center study was to investigate the discriminative potential of metabolite profiles obtained from 3T scanners in classifying pediatric brain tumors.MethodsA total of 41 pediatric patients with brain tumors (17 medulloblastomas, 20 pilocytic astrocytomas, and 4 ependymomas) were scanned across four different hospitals. Raw spectroscopy data were processed using TARQUIN. Borderline synthetic minority oversampling technique was used to correct for the data skewness. Different classifiers were trained using linear discriminative analysis, support vector machine, and random forest techniques.ResultsSupport vector machine had the highest balanced accuracy for discriminating the three tumor types. The balanced accuracy achieved was higher than the balanced accuracy previously reported for similar multi‐center dataset from 1.5T magnets with echo time 20 to 32 ms alone.ConclusionThis study showed that 3T MRS can detect key differences in metabolite profiles for the main types of childhood tumors. Magn Reson Med 79:2359–2366, 2018. © 2017 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

PEDIATRIC IMAGING P ediatric high-grade gliomas (HGGs) are tumors associated with poor overall survival (1,2). Since the recognition of the new tumoral type of diffuse midline gliomas (DMGs) H3 K27 mutant in the 2016 World Health Organization classification, four subtypes of DMG have been defined: DMG H3.3 mutant, DMG H3.1 mutant, DMG H3 wild type with enhancer of zest homologs inhibitory protein (EZHIP) overexpression, and DMG epidermal growth factor receptor (EGFR) mutant (3-5). The subtyping of H3 K27 mutants is justified by common biologic characteristics based on associated mutations and transcriptomic and methylation profiling ( 6). This has led to a better understanding of the biologic characteristics and treatment options for patients with these tumors, which Background: Diffuse midline gliomas (DMG) are characterized by a high incidence of H3 K27 mutations and poorer outcome. The HERBY trial has provided one of the largest cohorts of pediatric DMGs with available radiologic, histologic-genotypic, and survival data. Purpose: To define MRI and molecular characteristics of DMG. Materials and Methods:This study is a secondary analysis of a prospective trial (HERBY; ClinicalTrials.gov identifier, NCT01390948) undertaken between October 2011 and February 2016. Among 121 HERBY participants, 50 had midline nonpontine-based tumors. Midline high-grade gliomas were reclassified into DMG H3 K27 mutant, H3 wild type with enhancer of zest homologs inhibitory protein overexpression, epidermal growth factor receptor mutant, or not otherwise stated. The epicenter of each tumor and other radiologic characteristics were ascertained from MRI and correlated with the new subtype classification, histopathologic characteristics, surgical extent, and outcome parameters. Kaplan-Meier curves and log-rank tests were applied to determine and describe survival differences between groups.Results: There were 42 participants (mean age, 12 years 6 4 [SD]; 23 girls) with radiologically evaluable thalamic-based DMG. Eighteen had partial thalamic involvement (12 thalamopulvinar, six anteromedial), 10 involved a whole thalamus, nine had unithalamic tumors with diffuse contiguous extension, and five had bithalamic tumors (two symmetric, three partial). Twenty-eight participants had DMG H3 K27 mutant tumors; there were no differences in outcome compared with other DMGs (n = 4). Participants who underwent major debulking or total or near-total resection had longer overall survival (OS): 18.5 months vs 11.4 months (P = .02). Enrolled participants who developed leptomeningeal metastatic dissemination before starting treatment had worse outcomes (event-free survival, 2.9 months vs 8.0 months [P = .02]; OS, 11.4 months vs 18.5 months [P = .004]). Conclusion:Thalamic involvement of diffuse midline gliomas ranged from localized partial thalamic to holo-or bithalamic with diffuse contiguous spread and had poor outcomes, irrespective of H3 K27 subtype alterations. Leptomeningeal dissemination and less than 50% surgical resection were adverse risk facto...

MRS can provide high accuracy in the diagnosis of childhood brain tumours when combined with machine learning. A feature selection method such as principal component analysis is commonly used to reduce the dimensionality of metabolite profiles prior to classification. However, an alternative approach of identifying the optimal set of metabolites has not been fully evaluated, possibly due to the challenges of defining this for a multi‐class problem. This study aims to investigate metabolite selection from in vivo MRS for childhood brain tumour classification. Multi‐site 1.5 T and 3 T cohorts of patients with a brain tumour and histological diagnosis of ependymoma, medulloblastoma and pilocytic astrocytoma were retrospectively evaluated. Dimensionality reduction was undertaken by selecting metabolite concentrations through multi‐class receiver operating characteristics and compared with principal component analysis. Classification accuracy was determined through leave‐one‐out and k‐fold cross‐validation. Metabolites identified as crucial in tumour classification include myo‐inositol (P < 0.05, AUC=0.81±0.01), total lipids and macromolecules at 0.9 ppm (P < 0.05, AUC=0.78±0.01) and total creatine (P < 0.05, AUC=0.77±0.01) for the 1.5 T cohort, and glycine (P < 0.05, AUC=0.79±0.01), total N‐acetylaspartate (P < 0.05, AUC=0.79±0.01) and total choline (P < 0.05, AUC=0.75±0.01) for the 3 T cohort. Compared with the principal components, the selected metabolites were able to provide significantly improved discrimination between the tumours through most classifiers (P < 0.05). The highest balanced classification accuracy determined through leave‐one‐out cross‐validation was 85% for 1.5 T 1H‐MRS through support vector machine and 75% for 3 T 1H‐MRS through linear discriminant analysis after oversampling the minority. The study suggests that a group of crucial metabolites helps to achieve better discrimination between childhood brain tumours.

No abstract

presents an evaluation of the radiological imaging of the HERBY study, which is combined with molecular and pathological tumor characterization. This represents a more detailed post-hoc analysis than undertaken in the recently published results of the primary study endpoints: safety and event free survival. In depth assessment of the heterogeneous nature of pediatric HGG employing all three modalities underlines the importance of anatomical localization, surgical resectability, chemo-radiotherapeutic response prediction and stratification, incidence of leptomeningeal (and subependymal) dissemination and pseudoprogression. Distinctive imaging features of diffuse midline gliomas associated with H3 K27M mutations are described and contrasted with other midline and cerebral hemispheric pediatric HGGs. This study provides important information to help define response assessment in neuro-oncology specific to pediatric HGG.

BackgroundAssessment of treatment response by measuring tumor size is known to be a late and potentially confounded response index. Serial diffusion MRI has shown potential for allowing earlier and possibly more reliable response assessment in adult patients, with limited experience in clinical settings and in pediatric brain cancer. We present a retrospective study of clinical MRI data in children with high-grade brain tumors to assess and compare the values of several diffusion change metrics to predict treatment response.MethodsEighteen patients (age range, 1.9–20.6 years) with high-grade brain tumors and serial diffusion MRI (pre- and posttreatment interval range, 1–16 weeks posttreatment) were identified after obtaining parental consent. The following diffusion change metrics were compared with the clinical response status assessed at 6 months: (1) regional change in absolute and normalized apparent diffusivity coefficient (ADC), (2) voxel-based fractional volume of increased (fiADC) and decreased ADC (fdADC), and (3) a new metric based on the slope of the first principal component of functional diffusion maps (fDM).ResultsResponders (n = 12) differed significantly from nonresponders (n = 6) in all 3 diffusional change metrics demonstrating higher regional ADC increase, larger fiADC, and steeper slopes (P < .05). The slope method allowed the best response prediction (P < .01, η2 = 0.78) with a classification accuracy of 83% for a slope of 58° using receiver operating characteristic (ROC) analysis.ConclusionsWe demonstrate that diffusion change metrics are suitable response predictors for high-grade pediatric tumors, even in the presence of variable clinical diffusion imaging protocols.